Benchmarking Deep Learning for Time Series: Challenges and Directions

被引：0

作者：

Huang, Xinyuan ^{[1
]}

Fox, Geoffrey C. ^{[2
]}

Serebryakov, Sergey ^{[3
]}

Mohan, Ankur ^{[4
]}

Morkisz, Pawel ^{[5
,6
]}

Dutta, Debojyoti ^{[1
]}

机构：

[1] Cisco Syst, San Jose, CA 95134 USA

[2] Indiana Univ, Bloomington, IN USA

[3] Hewlett Packard Enterprise, San Jose, CA USA

[4] In Q Tel, Arlington, VA USA

[5] Nvidia, Warsaw, Poland

[6] AGH Univ Sci & Technol, Krakow, Poland

来源：

2019 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) | 2019年

关键词：

machine learning; deep learning; time series; performance; benchmark; CLASSIFICATION;

D O I：

10.1109/bigdata47090.2019.9005496

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Deep learning for time series is an emerging area with close ties to industry, yet under represented in performance benchmarks for machine learning systems. In this paper, we present a landscape of deep learning applications applied to time series, and discuss the challenges and directions towards building a robust performance benchmark of deep learning workloads for time series data.

引用

页码：5679 / 5682

页数：4

共 50 条

[31] Mcfly: Automated deep learning on time series
van Kuppevelt, D.
Meijer, C.
Huber, F.
van der Ploeg, A.
Georgievska, S.
van Hees, V. T.
SOFTWAREX, 2020, 12
[32] Deep learning for time series classification: a review
Fawaz, Hassan Ismail
Forestier, Germain
Weber, Jonathan
Idoumghar, Lhassane
Muller, Pierre-Alain
DATA MINING AND KNOWLEDGE DISCOVERY, 2019, 33 (04) : 917 - 963
[33] Deep imputation of missing values in time series health data: A review with benchmarking
Kazijevs, Maksims
Samad, Manar D.
JOURNAL OF BIOMEDICAL INFORMATICS, 2023, 144
[34] Deep learning based infrared small object segmentation: Challenges and future directions
Yang, Zhengeng
Yu, Hongshan
Zhang, Jianjun
Tang, Qiang
Mian, Ajmal
INFORMATION FUSION, 2025, 118
[35] Breast cancer detection using deep learning techniques: challenges and future directions
Muhammad Saad Shahid
Azhar Imran
Multimedia Tools and Applications, 2025, 84 (6) : 3257 - 3304
[36] Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, Laith
Zhang, Jinglan
Humaidi, Amjad J.
Al-Dujaili, Ayad
Duan, Ye
Al-Shamma, Omran
Santamaria, J.
Fadhel, Mohammed A.
Al-Amidie, Muthana
Farhan, Laith
JOURNAL OF BIG DATA, 2021, 8 (01)
[37] Formal methods enhance deep learning for smart cities: Challenges and future directions
Ma, Meiyi
XRDS: Crossroads, 2022, 28 (03): : 42 - 46
[38] Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Laith Alzubaidi
Jinglan Zhang
Amjad J. Humaidi
Ayad Al-Dujaili
Ye Duan
Omran Al-Shamma
J. Santamaría
Mohammed A. Fadhel
Muthana Al-Amidie
Laith Farhan
Journal of Big Data, 8
[39] Deep Learning for Diabetic Retinopathy Analysis: A Review, Research Challenges, and Future Directions
Nadeem, Muhammad Waqas
Goh, Hock Guan
Hussain, Muzammil
Liew, Soung-Yue
Andonovic, Ivan
Khan, Muhammad Adnan
SENSORS, 2022, 22 (18)
[40] Machine and Deep Learning for IoT Security and Privacy: Applications, Challenges, and Future Directions
Bharati, Subrato
Podder, Prajoy
SECURITY AND COMMUNICATION NETWORKS, 2022, 2022

← 1 2 3 4 5 →